Skip to content
Back to search

biomate-bioconductor-kb

BioMate-KB Bioconductor Skills — 200 packages (top 100 by downloads + 100 rising stars) as vignette-grounded Claude/agent skills, with per-package workflow recipes

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/biomate-ai--biomate-bioconductor-kb/badge.svg)](/listings/biomate-ai--biomate-bioconductor-kb)

HTML

<a href="/listings/biomate-ai--biomate-bioconductor-kb"><img src="/api/listings/biomate-ai--biomate-bioconductor-kb/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 218 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # BioMate-KB — Bioconductor Skills
  2. **200 Bioconductor packages — the top 100 most-downloaded plus the top 100 rising stars — formatted as Claude Code Skills.**
  3. A skill bundle in [Claude Code Skills](https://docs.anthropic.com/en/docs/claude-code/skills-overview) format. It covers the 100 most-used Bioconductor packages **and** the top 100 rising-star packages (newly released since ~2021 and fast-growing) from the BioMate-KB knowledge base. Each skill teaches Claude when to choose a package, **the workflows it supports** (each analysis as a recipe), what parameters to set, how to interpret results, and what pitfalls to avoid.
  4. ## What's here
  5. ```
  6. skills/ (200 packages · 12 domains) ⭐ = rising star
  7. ├── transcriptomics/ (97 — DESeq2, edgeR, limma · ⭐ standR, Voyager, sechm, crisprScore)
  8. ├── genomics/ (33 — GenomicRanges, Biostrings · ⭐ rBLAST, syntenet, ggmanh)
  9. ├── general/ (19 — Biobase, DOSE · ⭐ immunotation, faers, mosbi)
  10. ├── proteomics/ (16 — MSnbase, mixOmics, mzR · ⭐ MatrixQCvis, MsDataHub, TargetDecoy)
  11. ├── epigenomics/ (10 — ChIPseeker, minfi · ⭐ HiCExperiment, HiContacts, epigraHMM)
  12. ├── single-cell/ (8 — SingleCellExperiment · ⭐ demuxmix, hoodscanR, MuData)
  13. ├── variant-calling/ (4 — VariantAnnotation, snpStats, vsn)
  14. ├── metagenomics/ (4 — phyloseq, microbiome, DirichletMultinomial)
  15. ├── imaging/ (4 — flowCore, EBImage · ⭐ lisaClust, cytoviewer)
  16. ├── annotation/ (2 — biomaRt, KEGGgraph)
  17. ├── enrichment/ (2 — enrichplot, ReactomePA)
  18. └── metabolomics/ (1 — ⭐ rgoslin)
  19. ```
  20. A package that supports multiple analyses lists each as a `### ` recipe under a **`## Workflows`** section (e.g. DESeq2 → standard / multi-factor / LRT; crisprscore → on-target / off-target / indel scoring). The most-used 100 cover ~56% of Bioconductor analysis-package download volume; the rising-star 100 surface newly-important methods before they reach the top by volume. Beyond this 200-package sample, the full BioMate KB has runnable workflows for **1,818** Bioconductor packages — **~87% of analysis-package download volume** — available via [BioMate Cloud](https://biomate.ai).
  21. **Bioconductor version:** these skills are grounded against **Bioconductor 3.21** (pinned explicitly — `release` is a moving pointer that drops packages as it advances, e.g. several rising stars dropped out of 3.23). The pinned version is recorded in `MANIFEST.json` (`bioconductor_version`); re-fetch a different snapshot with `BIOC_VERSION=… python3 extraction/fetch_authoritative_sources.py`.
  22. ## Full package list
  23. All **200 packages** — with category, description, and the workflows each one supports — are in
  24. **[PACKAGES.md](PACKAGES.md)** (one page, four columns; ⭐ marks rising stars).
  25. ### Packages per domain
  26. ![Packages per domain](assets/packages_per_domain.png)
  27. ### Workflows per domain
  28. A package with multiple analyses contributes one `### ` recipe subsection per workflow — **390 workflows
  29. across the 200 packages; 89 are multi-workflow** (e.g. DESeq2 → DE / multi-factor / QC-transform /
  30. LRT; crisprScore → 6 scoring recipes).
  31. ![Workflows per domain](assets/workflows_per_domain.png)
  32. ## How these 200 were selected
  33. Two ranked sets of 100:
  34. - **Top 100 by downloads** — ranked purely by the official Bioconductor download score
  35. (`bioc_pkg_scores.tab`). These cover **~56% of Bioconductor analysis-package download volume**. Because the rank
  36. is by raw volume, this set includes both **analysis tools** (DESeq2, edgeR, limma, fgsea, …) and
  37. the **foundational data-structure / I/O / annotation** packages nearly every analysis imports
  38. (GenomicRanges, Biostrings, SingleCellExperiment, AnnotationHub, …).
  39. - **Top 100 rising stars** — restricted to **analysis** packages (infrastructure, data-container,
  40. and GUI packages excluded), recently released (first release ≥ 2021) and fast-growing in 2025
  41. (year-over-year download growth + ≥ 3,000 distinct download IPs), ranked by 2025 downloads. They
  42. surface newly-important methods *before* they reach the top by raw volume.
  43. Together these 200 packages cover **~57% of Bioconductor's analysis-package download volume**
  44. (foundational infrastructure and data-container packages — which alone are ~40% of raw
  45. downloads — are not counted as analysis volume). The full **BioMate-KB** goes much further:
  46. runnable workflows for **1,818** analysis packages — **~87% of analysis-package download
  47. volume**.
  48. > **Note on domains.** Domain labels come from BioMate's catalog and are intentionally coarse —
  49. > *transcriptomics* is a broad catch-all that absorbs most single-cell, spatial, and gene-set tools
  50. > (scater / scran / monocle / SingleR are single-cell; fgsea / GSVA are enrichment) — which is why
  51. > it dominates the charts, and why the small *single-cell* (8) and *annotation* (2) folders are
  52. > remnants of the same imperfect classifier rather than clean boundaries. We keep BioMate's labels
  53. > for traceability; treat the domain folders as a rough guide, not a strict ontology.
  54. **Our contribution** — unique among public skill libraries:
  55. 1. **The only per-R/Bioconductor-package library** — **200** packages here, **1,818** in the full KB.
  56. Every other public set is task-oriented or Python-centric; none provide per-package R/Bioconductor
  57. knowledge at this depth (the closest R one, wolf5996, has 13 skills and covers R *packaging*, not
  58. Bioconductor analysis).
  59. 2. **Vignette-grounded & fact-verified** — every R function named in a skill is verified to appear in
  60. that package's own Bioconductor vignette (mean verify **0.91**), not free-form LLM prose.
  61. 3. **Per-package workflow recipes** — a package's distinct analyses are explicit `### ` recipes
  62. (**390** across the 200) — *how to run it*, not just *what it is*.
  63. 4. **Executable backing** — the same knowledge runs as managed, validated workflows on
  64. [BioMate Cloud](https://www.biomate.ai) for **1,818** packages.
  65. ## Tutorial: Bulk RNA-seq → DESeq2 → STRINGdb Gene Interaction Network
  66. This walkthrough shows how BioMate routes a plain-English bulk RNA-seq request through DESeq2, GO enrichment, and an **interactive STRINGdb protein-protein interaction panel** — without writing R code.
  67. **What the demo covers:**
  68. - Natural-language workflow routing to DESeq2 + clusterProfiler
  69. - Differential expression on 120 samples (human GRCh38, control vs treated)
  70. - GO enrichment (enrichGO) identifying apoptotic regulation as the top pathway
  71. - **Interactive gene interaction panel** — STRINGdb network visualization of the top 2,841 DEGs, with nodes coloured by log₂FC and edges weighted by STRING confidence score
  72. - AI findings summary + citable methods section + citation export
  73. [![BioMate AI | Bulk RNA-seq: DESeq2 + GO enrichment, no R code needed](https://img.youtube.com/vi/WL8Jk7M8n1g/maxresdefault.jpg)](https://youtu.be/WL8Jk7M8n1g)
  74. *▶ Click the image above to watch the tutorial on YouTube.*
  75. For all tutorials (single-cell Seurat, DNA methylation, bispecific antibody design, CAR-T, base editing, GLP-1 modality selection, BCMA myeloma triage) see the **[BioMate Tutorial Page →](https://biomate.ai/tutorials.html)**
  76. ---
  77. ## Want the full collection?
  78. This bundle covers 200 Bioconductor packages (top 100 by downloads + 100 rising stars). **[BioMate AI](https://www.biomate.ai)** gives you:
  79. - **Broad Bioconductor coverage** — runnable workflows for **1,818** packages (**~87%** of analysis-package download volume), plus nf-core and drug-discovery pipelines across genomics, proteomics, and more
  80. - **Efficient parallel computing** — workflows run in the cloud with automatic scaling, no cluster setup required
  81. - **Interactive visualization & analysis** — inspect, filter, and re-run results through linked charts and per-step QC dashboards, with AI-assisted interpretation that links every claim back to the underlying data
  82. - **Reproducible reporting** — methods and results documents generated with complete parameter and software-version provenance, formatted for publication and audit
  83. **Free for academic and non-profit researchers** — [register at www.biomate.ai](https://www.biomate.ai) (no credit card required).
  84. Commercial plans available. Questions or collaboration inquiries: [contact@biomate.ai](mailto:contact@biomate.ai)
  85. ## How to use
  86. ```bash
  87. # Clone
  88. git clone https://github.com/bioMate-AI/biomate-bioconductor-kb.git
  89. cd biomate-bioconductor-kb
  90. # Install all skills into Claude Code (global)
  91. find skills -name "SKILL.md" | while read f; do
  92. pkg=$(dirname "$f" | xargs basename)
  93. cp "$f" ~/.claude/skills/bioconductor-${pkg}.md
  94. done
  95. ```
  96. Or copy a single domain:
  97. ```bash
  98. # Only RNA-seq DE skills
  99. find skills/transcriptomics -name "SKILL.md" | while read f; do
  100. pkg=$(dirname "$f" | xargs basename)
  101. cp "$f" ~/.claude/skills/bioconductor-${pkg}.md
  102. done
  103. ```
  104. Each `SKILL.md` is a self-contained Claude Code skill file — Claude discovers it automatically once it's in `~/.claude/skills/` (global) or `.claude/skills/` (project-level).
  105. ## Ranking source
  106. Packages are ordered by Bioconductor's official monthly download score:
  107. - Source: <https://bioconductor.org/packages/stats/bioc/bioc_pkg_scores.tab>
  108. - Snapshot taken: 2026-05-21
  109. - Top 100 by download score + 100 analysis rising stars = 200 packages, together **~57% of Bioconductor analysis-package download volume**
  110. Because the ranking is by download volume, the bundle includes both **analysis tools** (DESeq2, edgeR, limma, fgsea, …) and the **core data-structure, I/O, and annotation packages** that nearly every analysis depends on (GenomicRanges, Biostrings, SingleCellExperiment, AnnotationHub, …) — the latter rank highly precisely because they are imported everywhere. Both are useful to an agent: the analysis packages teach *how to analyze*, the foundational ones *how to represent and load* the data.
  111. ## Knowledge layer, not pipelines
  112. These skills are the **knowledge layer** — when and why to use each package, with parameters, assumptions, pitfalls, and alternatives. They are not runnable pipelines and carry no infrastructure details.
  113. **BioMate hosts and executes these workflows for you** — managed compute, automated QC, and reproducible outputs — powered by this same Bioconductor know-how. For end-to-end cloud execution, see **[BioMate](https://www.biomate.ai)**.
  114. ## License
  115. - **Skill content** (`skills/**/*.md`, `MANIFEST.json`): **CC-BY-4.0** — share + adapt with attribution.
  116. - **Extraction scripts** (`extraction/*.py`): **Apache-2.0** — use, modify, distribute.
  117. - **Underlying Bioconductor packages** retain their own (mostly Artistic-2.0 / GPL) licenses.
  118. ## Citation
  119. If you use this skill bundle in research, please cite:
  120. > Zhang, Y. (2026). *BioMate-KB: A Real-Execution-Validated Workflow Knowledge Base for Bioconductor* (3.0). Zenodo. https://doi.org/10.5281/zenodo.20616356
  121. And, for the execution-grounding methodology:
  122. > Zhang, Y. (2026). *Structure Grounding Is Not Enough: Real Execution as the Ground Truth for LLM-Generated Bioinformatics Workflows* (Version v3). Zenodo. https://doi.org/10.5281/zenodo.20616544
  123. Concept DOIs (always resolve to the latest version): BioMate-KB — https://doi.org/10.5281/zenodo.20616355 · Structure Grounding — https://doi.org/10.5281/zenodo.20616543
  124. ## Regenerating the bundle
  125. ```bash
  126. # Re-fetch the latest Bioconductor download scores
  127. curl -O https://bioconductor.org/packages/stats/bioc/bioc_pkg_scores.tab
  128. # Regenerate the download-ranked set (top 100 by default).
  129. # The 100 rising-star skills are a separately-curated set (analysis packages,
  130. # first release >= 2021, ranked by 2025 download growth) generated per-package
  131. # via extract_skill.py, then vignette-grounded with enrich_v2_grounded.py.
  132. python3 extraction/generate_bundle.py --top 100
  133. # Single package
  134. python3 extraction/extract_skill.py \\
  135. --db <path-to-biomate-knowledge-db> \\
  136. --pkg DESeq2 \\
  137. --out my-deseq2-skill.md
  138. ```
  139. The extraction code (`extraction/extract_skill.py`) is intentionally minimal (~300 lines) and reads only from BioMate's public knowledge fields — `tool_knowledge.{use_cases, limitations, alternatives, recommended_parameters, primary_citation, benchmark_papers}` and `tools.scientific_context`. Internal and infrastructure fields are excluded.
  140. ## Versioning
  141. **v2.0.0** (2026-06-15) — full history in **[CHANGELOG.md](CHANGELOG.md)**. Skills are pinned to
  142. **Bioconductor 3.21** (recorded in `MANIFEST.json`).
  143. Since v1.0.0: coverage doubled to **200 packages** (added the top 100 rising stars), per-package
  144. `## Workflows` recipes, and a full package table + coverage charts.
  145. Planned: track new Bioconductor releases, expand coverage (top-1000 if community demand justifies),
  146. and refine `SKILL.md` sections (Q&A, gotchas, more examples).
  147. ## Contributing
  148. Open an issue or PR for:
  149. - Errors in any SKILL.md
  150. - Suggestions for new sections to extract
  151. - Packages missing from the top-100 / rising-star sets that should be included
  152. ## Acknowledgments
  153. Bioconductor download statistics published by the Bioconductor Core Team. SKILL.md format from [Anthropic Claude Code](https://docs.anthropic.com/en/docs/claude-code/skills-overview).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.